© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23728
    Prev
    Next
    INDEX
    Explanations

    percentage increases and growth rates over specific time periods

    oai_token-act-pair · gpt-3.5-turbo

    percent increases or decreases in statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bol
    -0.65
    bart
    -0.64
    ullah
    -0.62
    oring
    -0.62
    greg
    -0.61
    sonian
    -0.60
    ctor
    -0.60
    æĦ
    -0.59
    rub
    -0.59
    mp
    -0.59
    POSITIVE LOGITS
     previous
    1.11
     prior
    0.90
     2007
    0.86
     2015
    0.85
     earlier
    0.85
     2009
    0.85
     last
    0.84
     2011
    0.83
     2008
    0.81
     2014
    0.81
    Activations Density 0.164%

    No Known Activations